Diffus
Inizia
modelli/Ionsyx - V2.0 - Base

Ionsyx - V2.0 - Base

Old_Arctenox
|
11/15/2026
|
4:00:58 PM
| Discussion
Nessuna immagine trovata per il modello

Prompt Consigliati

(masterpiece), best quality, amazing quality, absurdres

masterpiece, best quality, absurdres

(masterpiece), best quality, absurdres

Prompt Negativi Consigliati

worst quality, artist sign, artist name, username, signature, logo, four fingers, six fingers

worst quality, worst detail, very displeasing, artistic error, old, early, artist sign, artist name, username, signature, logo, bokeh

worst quality, low quality, low res, worst detail, bad quality, old, early, displeasing, very displeasing, bokeh, artistic error, artist sign, artist name, username, signature, logo, bad proportions, bad hands, mutated hands, four fingers, six fingers, glowing eyes

Parametri Consigliati

samplers

Euler_Ancestral, Euler

steps

7 - 25

cfg

3 - 4

Suggerimenti

Bad promoting will result in bad images; this model suits users with some experience.

You may need to generate a few times to achieve desired results.

Use higher resolutions for better base generation on full-body images.

Negative prompt weights above 1.4 can cause image artifacts.

Feel free to leave critiques and suggestions to help improve the model.

Tip, like, or follow if you want to support future LoRA projects and model auctions.

Model files are embedded with the workflow used to create them, though it may need optimization.

Punti Salienti della Versione

This is a block merge with my private merge, with finetuning it with a LoRA made from images from the Va'nsyx V1 - Base, as well. 71% of the new clip in the model is my private merge.

This version should have slightly better coherence, some more detail and more character lora compatibility, if used properly. Also, the style in V2 - Base, is even more basic as to allow for more LoRAs to be compatible.

Note: Also the model does take a bit to get used to, I still haven't gotten used to it myself :P. By the way most donated buzz will be used for mostly bidding on this model made by Arctenox (Me), as always.

Sponsor del Creatore

Model available for bidding onsite; minimum 1 yellow buzz to promote inclusion in generator.

Model can be found and supported on Civitai - Hex Base Illustrious and Civitai - Hex Ionsyx Illustrious.

Also available on tensor.art for site generation.

Support the author at Arctenox on Civitai.

Rebranded and Updated versions can be found here: https://civitai.com/models/2184797/hex-base-illustrious
Or you can go here to check out a mix of a few versions of Ionsyx which is also technically a update of this checkpoint but less of a rebrand: https://civitai.com/models/2307532/hex-ionsyx-illustrious

Don't forget to bid on this model if you'd like to use it onsite!

V3.9+ (In-between versions of V5.2 and V3.5) Is here as a sort of a revised version of V1.0 and some other stuff in it and removed a couple stuff plus I tried to make sure it's still mostly V3.5 - Base mix with the Revised Version: https://civitai.com/models/1612860

Welcome to Ionsyx my Frankenstein of a merge model some people who used it regularly, call it and I wholly agree. Don't worry though it can guarantee from myself and others that the model is good. However I don't recommend starting with this if your new to illustrious or Danbooru in general unless you like the challenge since bad promoting will result in bad images.

Feel free to leave suggestions on what I can put in here to fix issues you may get. Plus feel free to leave critiques that are either bad or good that are this checkpoint model only stuff, I like to be able to improve.

Also feel free to publish images made from this, it can help people find the model and find your IMGs, also I like checking my model pages, so it's usually a free like from me if I like the images posted. And remember, you can always bid at minimum 1 yellow buzz on models you like at the auction page to see them get into the generator. :D

Renamed from Va'nsyx to Ionsyx so it's name is more easily remembered.

  • Steps: 20+ / Depends on the Sampler and Scheduler used.

  • CFG: 3.0+

  • Sampler: Euler_Ancestral / (Mostly a personal preference and starting point. Although I don't recommend Euler)

  • Scheduler: Normal (Mostly a personal preference of mine.)

  • ADetailers / Upscalers / HiRes | Base generation for characters is kind of bad if you use Euler.

  • Steps: 20+ / Depends on the Sampler and Scheduler used.

  • CFG: 4.5+

  • Sampler: Euler / (Mostly a personal preference and starting point.)

  • Scheduler: Normal (Mostly a personal preference and starting point.)

  • ADetailers / Upscalers / HiRes | Base generation for characters is kind of bad.
    Note: Similar stuff to V2.5 but you may need to use higher resolutions for decent/good base gens on full body images. Also thumbnail images are not base generation, they went through upscales and detailers.

  • Steps: 20+ / Depends on the Sampler and Scheduler used.

  • CFG: 4.5+

  • Sampler: Euler / (Mostly a personal preference and starting point.)

  • Scheduler: Normal (Mostly a personal preference and starting point.)

  • ADetailers / Upscalers / HiRes | Base generation for characters is kind of bad.


    Note: You may need to generate a few times, if you don't get what you want exactly, as always. This also has some Illustrious V2.0 in it, so people use at minimum these quality tags or other quality tags plus you can use some NL to ground the prompt:

    masterpiece, best quality, absurdres

    Also you may need to use this negative to start with or whatever other negative tags you want to use:

    worst quality, artist sign, artist name, username, signature, logo, four fingers, six fingers

    Settings V2.5 doesn't work for:

  • Some negative prompt weighting. Weights above 1.4 for some negative tags can cause the image to fry.

  • Steps: 7 to 30+ / Depends on the Sampler and Scheduler used. (Probably want to use around 20 steps, if you want to upscale or whatever else)

  • CFG: 4+

  • Sampler: Euler Ancestral / Euler (Needs tested further)

  • Scheduler: Normal (Needs tested further)
    Note: You may need to generate a few times, if you don't get what you want exactly, as always.

  • Steps: 20 - 30+ / (Probably want to use 20 steps, if you want to upscale or whatever else)

  • CFG: 4+

  • Sampler: Euler (Needs tested further)

  • Scheduler: Normal (Needs tested further)
    Note: Sometimes a Face Detailer, Upscale, or rarely Hi-Res Fix. Also you may need to generate a few times, hands are a bit iffy.

worst quality, worst detail, very displeasing, artistic error, old, early, artist sign, artist name, username, signature, logo, bokeh

Note: You also can just use your own negative if it works. Also "(Needs tested further)" just means I haven't done anything past those things. You also don't really need a negative, but if you see some things wrong use one or few of those negatives I guess.

Here's a Base Positive Prompt you should use with most Illustrious + Noobai merge models:

(masterpiece), best quality, amazing quality, absurdres

Note: You don't have to weight masterpiece that's just me since I obtain results I want with it like that. ;P


Extra Unimportant Text:

Also feel free to tip, like or follow the model to show support to the model and me, only if you want because I only do this as a hobby, so the tips will go towards future LoRAs from me and bidding the model in the auction. Model will be available on tensor.art for site generation, as always (https://tensor.art/projects/847364693793431995). Files usually will be embedded with the workflow used to make it, sometimes my workflow for genning which needs optimized, so I don't suggest using it.


This model was made due to being inspired by images from princess_daphie in a DM. Thumbnail was of course still made using a 1060 Series GPU getting a 3060 12GB Upcoming Thursday (4/3/2025). - Arctenox

Note: I got the GPU a day or two early, so... the two first style versions were made on the new GPU. - Arctenox

⚠️ IF YOU'RE GOING TO STEAL MY (https://civitai.com/user/Arctenox) MODELS OR POST THEM SOMEWHERE ELSE, MAKE IT SO THE DOWNLOAD IS ENABLED, IF IT'S NOT THEN I KNOW A BOT UPLOADED IT.⚠️

https://civitai.com/models/1393785

Precedente
Seedream - v4.5
Nessuna immagine successiva
Usa questo modello

Dettagli del Modello

Tipo di modello

Checkpoint

Modello base

Illustrious

Versione del modello

V2.0 - Base

Hash del modello

5c5a910123

Creatore

Old_Arctenox's avatar
Old_Arctenox

Discussione

Per favore log in per lasciare un commento.

Immagini con anime

A silhouetted boy holding a bubble wand against a vibrant, surreal dusk sky releasing colorful glitching neon mist with a crescent moon and a distorted airplane in the background.
Illustrazione anime di Frieren con codini grigi e occhi verdi, sdraiata a piedi nudi su un letto con una camicia da notte bianca, che guarda indietro con un sorriso compiaciuto.
Ragazza anime con capelli rosa e arancioni che sorride con molti denti affilati e mostruosi che si estendono ampiamente, in piedi in un interno treno buio con luci tremolanti.
Ragazza in stile anime vestita con un outfit da maid gotica con accenti viola, inginocchiata e che tiene una replica di arma da fuoco, con tacchi neri.
Un soldato cyborg con una vistosa mano meccanica rossa e occhi gialli, che indossa un'uniforme militare nera, accovacciato in un corridoio di prigione macchiato di sangue con un sorriso malvagio e una lunga lingua grigia che sporge.
Una tranquilla scena nel bosco con una accogliente casetta della strega con tetto coperto di muschio accanto a uno stagno limpido, collegata da un ponte di legno tra una rigogliosa vegetazione.
Android femminile cibernetico che indossa una maschera a teschio bianca e nera con armatura mimetica, che tiene due pistole futuristiche in una posa dinamica sotto una struttura in un ambiente roccioso.
Una donna giapponese snella con pelle di porcellana e capelli neri corvini indossa un elegante abito nero avant-garde e si presenta con sicurezza contro un cielo invernale olografico con tonalità pastello morbide, evocando una mattina d'inverno da sogno.
Una figura angelica con ali bianche luminose si erge tra rovine crepate tenendo una spada orizzontale luminosa, circondata da un ambiente oscuro, misterioso e cinematografico.
Personaggio femminile in stile anime con capelli scuri, che indossa occhiali kaleidoscopici e lecca un lecca-lecca rosa e bianco, il suo viso trasparente si fonde in un vivido paesaggio onirico liquido di colori e luci.

Immagini con modello base

Scena fotorealistica di personaggi non morti tra zombie e scheletri che camminano attraverso un cimitero spettrale illuminato da jack-o'-lantern luminosi sotto un cielo scuro e minaccioso.